A neuron in machine learning, specifically in the context of neural networks, is a fundamental unit that mimics the behavior of biological neurons in the human brain. It receives input signals, processes them, and produces an output signal. Each neuron performs a simple calculation, like a weighted sum of its inputs, and then applies a non-linear function, often called an activation function, to this sum to produce an output.

How Neurons Function

In practice, neurons are arranged in layers within a neural network. An individual neuron receives inputs from either external data sources (in the case of the input layer) or the outputs of neurons from the previous layer. It then computes a weighted sum of these inputs, adds a bias term, and applies an activation function. The output of this process is then passed on to the next layer in the network. The weights and biases are the adjustable parameters of the network, which are tuned during the training process to minimize the network's error on training data.

Lakera LLM Security Playbook
Learn how to protect against the most common LLM vulnerabilities

Download this guide to delve into the most common LLM security risks and ways to mitigate them.

Related terms
untouchable mode.
Get started for free.

Lakera Guard protects your LLM applications from cybersecurity risks with a single line of code. Get started in minutes. Become stronger every day.

Join our Slack Community.

Several people are typing about AI/ML security. 
Come join us and 1000+ others in a chat that’s thoroughly SFW.